Yuan Xie

Yuan Xie

Auto-generated profile, based on publicly available information

Yuan Xie

The Hong Kong University of Science and Technology, Hong Kong, Hong Kong

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 October 2018 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
CZChangqing Zhang
Changqing Zhang
HFHuazhu Fu
Huazhu Fu
QHQinghua Hu
Qinghua Hu
XCXiaochun Cao
Xiaochun Cao
YXYuan Xie
Yuan Xie
DXDong Xu
Dong Xu
Subspace clustering is an effective method that has been successfully applied to many applications. Here we propose a novel subspace clustering model for multi-view data using a latent representation termed Latent Multi-View Subspace Clustering (LMSC). Unlike most existing single-view subspace clustering methods, which directly reconstruct data points using original features, our method explores underlying complementary information from multiple views and simultaneously seeks the underlying latent representation. Using the complementarity of multiple views, the latent representation depicts data more comprehensively than each individual view, accordingly making subspace representation more accurate and robust. We proposed two LMSC formulations: linear LMSC (lLMSC), based on linear correlations between latent representation and each view, and generalized LMSC (gLMSC), based on neural networks to handle general relationships. The proposed method can be efficiently optimized under the Augmented Lagrangian Multiplier with Alternating Direction Minimization (ALM-ADM) framework. Extensive experiments on diverse datasets demonstrate the effectiveness of the proposed method.

6 April 2018 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
YXYuan Xie
Yuan Xie
DTDacheng Tao
Dacheng Tao
WZWensheng Zhang
Wensheng Zhang
YLYan Liu
Yan Liu
LZLei Zhang
Lei Zhang
YQYanyun Qu
Yanyun Qu

1 January 2020 in Neural Networks
Verified
Journal Article
Closed access
Lei DengLei Deng
Lei Deng
YWYujie Wu
Yujie Wu
XHXing Hu
Xing Hu
LLLing Liang
Ling Liang
YDYufei Ding
Yufei Ding
YXYuan Xie
Yuan Xie

1 December 2020 in Neural Networks
Verified
Journal Article
Closed access
WHWeihua He
Weihua He
YWYuJie Wu
YuJie Wu
Lei DengLei Deng
Lei Deng
GGuoqi Li
Guoqi Li
HWHaoyu Wang
Haoyu Wang
YXYuan Xie
Yuan Xie

23 November 2017 in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
Verified
Journal Article
Open access
LXLixue Xia
Lixue Xia
WHWenqin Huangfu
Wenqin Huangfu
TTTianqi Tang
Tianqi Tang
XYXiling Yin
Xiling Yin
KCKrishnendu Chakrabarty
Krishnendu Chakrabarty
HYHuazhong Yang
Huazhong Yang
Emerging metal-oxide resistive switching randomaccess memory (RRAM) devices and RRAM crossbars have demonstrated their potential in boosting the speed and energyefficiency of analog matrix-vector multiplication. However, due to the immature fabrication technology, commonly occurring Stuck- At-Faults (SAFs) seriously degrade the computational accuracy of an RRAM-based Computing System (RCS). In this paper, we present a fault-tolerant framework for RCS. A Mapping Algorithm with inner fault tOlerance (MAO) is proposed to convert matrix parameters into RRAM conductances in RCS and tolerate SAFs by fully exploring the available mapping space. Two baseline redundancy schemes are proposed to ensure that RCS is effective when the percentage of faulty RRAM cells is high. To reduce the number of redundant RRAM cells when the SAFs follow a non-uniform distribution or an unknown distribution, a distribution-aware redundancy scheme and a re-configurable redundancy scheme are proposed to provide dynamic fault tolerance. Simulation results show that, the baseline redundancy schemes can improve the recognition accuracy of the MNIST dataset to almost the same as the RRAM-fault-free case, with an energy overhead of approximately 30%. When SAFs follow a non-uniform and an unknown distribution, the distributionaware and re-configurable schemes can reduce the number of redundant RRAM cells from more than 200% to less than 40% and 60%, respectively, without reducing the recognition accuracy.

30 March 2018 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
GDGuohao Dai
Guohao Dai
THTianhao Huang
Tianhao Huang
YCYuze Chi
Yuze Chi
JZJishen Zhao
Jishen Zhao
GSGuangyu Sun
Guangyu Sun
HYHuazhong Yang
Huazhong Yang
Large-scale graph processing requires the high bandwidth of data access. However, as graph computing continues to scale, it becomes increasingly challenging to achieve a high bandwidth on generic computing architectures. The primary reasons include: the random access pattern causing local bandwidth degradation, the poor locality leading to unpredictable global data access, heavy conflicts on updating the same vertex, and unbalanced workloads across processing units. Processing-in-memory has been explored as a promising solution to providing high bandwidth, yet open questions of graph processing on PIM devices remain in: (1) How to design hardware specializations and the interconnection scheme to fully utilize bandwidth of PIM devices and ensure locality; (2) How to allocate data and schedule processing flow to avoid conflicts and balance workloads. In this paper, we propose GraphH, a PIM architecture for graph processing on the Hybrid Memory Cube array, to tackle all four problems mentioned above. From the architecture perspective, we integrate SRAM-based On-chip Vertex Buffers to eliminate local bandwidth degradation; We also introduce Reconfigurable Double-Mesh Connection to provide high global bandwidth. From the algorithm perspective, partitioning and scheduling methods like Index Mapping Interval-Block and Round Interval Pair are introduced to GraphH, thus workloads are balanced and conflicts are avoided. Two optimization methods are further introduced to reduce synchronization overhead and reuse on-chip data. The experimental results on graphs with billions of edges demonstrate that GraphH outperforms DDR-based graph processing systems by up to two orders of magnitude and 5.12x speedup against the previous PIM design iscagraph.